Skip to main content
Docbot uses different AI models for different tasks. You can override the default models in your docbot.config.jsonc file.

​
Model ID format

All model IDs must follow the format provider/model-name:
  • openai/gpt-5.2
  • anthropic/claude-sonnet-4.5
  • google/gemini-3-flash
  • cohere/rerank-v3.5

​
Configuration

{
  "models": {
    "planning": "openai/gpt-5.2",
    "planningHeavy": "anthropic/claude-opus-4.5",
    "prose": "anthropic/claude-sonnet-4.5",
    "fast": "openai/gpt-5.2",
    "nano": "google/gemini-3-flash",
    "context": "google/gemini-3-pro-preview",
    "embedding": "openai/text-embedding-3-small",
    "embeddingLarge": "openai/text-embedding-3-large"
  }
}

​
Model types

​
models.planning
string
default:"openai/gpt-5.2"
Model used for planning and task orchestration.Format: provider/model-name
​
models.planningHeavy
string
default:"anthropic/claude-opus-4.5"
Model used for complex planning tasks that require deeper reasoning.Format: provider/model-name
​
models.prose
string
default:"anthropic/claude-sonnet-4.5"
Model used for writing documentation prose.Format: provider/model-name
​
models.fast
string
default:"openai/gpt-5.2"
Model used for quick operations that don’t require deep reasoning.Format: provider/model-name
​
models.nano
string
default:"google/gemini-3-flash"
Model used for very simple, high-speed operations.Format: provider/model-name
​
models.context
string
default:"google/gemini-3-pro-preview"
Model used for context analysis and understanding.Format: provider/model-name
​
models.embedding
string
default:"openai/text-embedding-3-small"
Model used for generating text embeddings for semantic search.Format: provider/model-name
​
models.embeddingLarge
string
default:"openai/text-embedding-3-large"
Model used for generating high-quality embeddings when precision is critical.Format: provider/model-name

​
AI Gateway requirement

Docbot currently requires a AI_GATEWAY_API_KEY environment variable for Vercel AI Gateway. Support for other providers is planned. 
export AI_GATEWAY_API_KEY=your_key_here

Configuration overview

Learn about all configuration options

Qdrant configuration

Configure vector database settings

Build docs developers (and LLMs) love

Get started for freeTalk to us